How Should I Get Started with Machine Learning without a Technical Background?

How can someone with almost no technical knowledge learn ML? originally appeared on Quora - the place to gain and share knowledge, empowering people to learn from others and better understand the world.

Answer by Ian Goodfellow, AI Research Scientist at Google Brain, on Quora:

If you have almost no technical knowledge but want to get started with machine learning, it’s important to master some of the basics, like linear algebra, probability, and python programming.

But you don’t need to know all of linear algebra (I don’t think I’ve ever used a QR decomposition outside the classroom), all of probability (we don’t usually do much involving combinatorics/re-ordering of sequences in deep learning), or all of python programming (a lot of the more obscure language features are actually forbidden at some companies).

I’d say maybe start by learning enough linear algebra, probability, and python programming that you can implement logistic regression yourself, using only python and numpy.

I think that if you read Deep Learning chapters 1–5, you should be able to learn everything you need for that project except the Python programming. It’s a little bit hard for me to know how feasible that is because it’s hard to put myself in the position of someone coming in with no technical knowledge. It will obviously take a lot of patience and effort to absorb that much material rapidly starting from zero, but we tried to put enough detail in the book that you could get that far.

This question originally appeared on Quora - the place to gain and share knowledge, empowering people to learn from others and better understand the world. You can follow Quora on Twitter, Facebook, and Google+. More questions:

• Adversarial Machine Learning: What are some new and exciting areas in adversarial machine learning research?
• Machine Learning: Which are the top 3 books that you would recommend in Machine Learning?
• Google Brain: What is Google Brain working on in 2017?